Hugging Face's logo

dzungpham
/
graphcodebert-code-classification

Transformers
Safetensors
detection
AI-generated
bert
Model card Files
xet
 Community
dzungpham commited on
Commit
28b4bc7
·
verified ·
1 Parent(s): 0054bd3

Upload training checkpoints and best model

Browse files
Files changed (21) hide show
  1. checkpoint-1000/model.safetensors +2 -2
  2. checkpoint-1000/optimizer.pt +2 -2
  3. checkpoint-1000/rng_state.pth +1 -1
  4. checkpoint-1000/scaler.pt +3 -0
  5. checkpoint-1000/scheduler.pt +1 -1
  6. checkpoint-1000/tokenizer.json +1 -6
  7. checkpoint-1000/trainer_state.json +531 -427
  8. checkpoint-1000/training_args.bin +2 -2
  9. checkpoint-1100/config.json +29 -0
  10. checkpoint-1100/merges.txt +0 -0
  11. checkpoint-1100/model.safetensors +3 -0
  12. checkpoint-1100/optimizer.pt +3 -0
  13. checkpoint-1100/rng_state.pth +3 -0
  14. checkpoint-1100/scaler.pt +3 -0
  15. checkpoint-1100/scheduler.pt +3 -0
  16. checkpoint-1100/special_tokens_map.json +51 -0
  17. checkpoint-1100/tokenizer.json +0 -0
  18. checkpoint-1100/tokenizer_config.json +58 -0
  19. checkpoint-1100/trainer_state.json +956 -0
  20. checkpoint-1100/training_args.bin +3 -0
  21. checkpoint-1100/vocab.json +0 -0
checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b58314c6827ac34bcd352ce1fc7950b1d20ca398a3a892afc4dae05a21ce8916
3
- size 503749208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dba0da560adadcbd863063b6d8a4d4b56290c3be335cf41f14a557b6fee1c9f
3
+ size 506505672
checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e5bd83a18fef7f081ebc6b4706dc3434cc22b7353d2021ca7d668463d93dc46
3
- size 1007621899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bdf390e9c9e5d555f636219141a77d3bb7ad8de7356aaf171bdfbbbf56a7182
3
+ size 1007622411
checkpoint-1000/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01417872332d957944438dd9b4b8729804838252520f015df0aea72edce6b540
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5183674b6e19178da7160a0d79f26425cdd2d73db6134e2a7310a7b772fca618
3
  size 14645
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5e3abecfb917c340b4d882625db5f9460551d58b56c250704864b7bc1aa3e4
3
+ size 1383
checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7ae580020b16556dd1a430705dd359df07f40b74863a29d02711598cf5fe41f
3
  size 1977
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c69cb9ab6a70db20a2d0ee7c18ddc9292442d3eec7b5ec05df69a67d327cf4b
3
  size 1977
checkpoint-1000/tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
checkpoint-1000/trainer_state.json CHANGED
@@ -1,746 +1,850 @@
1
  {
2
  "best_global_step": 1000,
3
- "best_metric": 0.9548451024890077,
4
  "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1000",
5
- "epoch": 0.06117704637220115,
6
- "eval_steps": 500,
7
  "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.0006117704637220115,
14
- "grad_norm": 5.2196149826049805,
15
- "learning_rate": 9.178990311065784e-08,
16
- "loss": 0.2114,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.001223540927444023,
21
- "grad_norm": 2.4952661991119385,
22
- "learning_rate": 1.937786843447221e-07,
23
- "loss": 0.179,
24
  "step": 20
25
  },
26
  {
27
- "epoch": 0.0018353113911660345,
28
- "grad_norm": 3.8488683700561523,
29
- "learning_rate": 2.9576746557878637e-07,
30
- "loss": 0.1949,
31
  "step": 30
32
  },
33
  {
34
- "epoch": 0.002447081854888046,
35
- "grad_norm": 3.7437973022460938,
36
- "learning_rate": 3.9775624681285064e-07,
37
- "loss": 0.2007,
38
  "step": 40
39
  },
40
  {
41
- "epoch": 0.0030588523186100575,
42
- "grad_norm": 3.8342156410217285,
43
- "learning_rate": 4.997450280469149e-07,
44
- "loss": 0.1828,
45
  "step": 50
46
  },
47
  {
48
- "epoch": 0.003670622782332069,
49
- "grad_norm": 3.510793685913086,
50
- "learning_rate": 6.017338092809792e-07,
51
- "loss": 0.1875,
52
  "step": 60
53
  },
54
  {
55
- "epoch": 0.0042823932460540805,
56
- "grad_norm": 3.223860740661621,
57
- "learning_rate": 7.037225905150434e-07,
58
- "loss": 0.1661,
59
  "step": 70
60
  },
61
  {
62
- "epoch": 0.004894163709776092,
63
- "grad_norm": 3.791808605194092,
64
- "learning_rate": 8.057113717491076e-07,
65
- "loss": 0.1762,
66
  "step": 80
67
  },
68
  {
69
- "epoch": 0.0055059341734981036,
70
- "grad_norm": 3.8649113178253174,
71
- "learning_rate": 9.077001529831719e-07,
72
- "loss": 0.1774,
73
  "step": 90
74
  },
75
  {
76
- "epoch": 0.006117704637220115,
77
- "grad_norm": 2.9645302295684814,
78
- "learning_rate": 1.0096889342172361e-06,
79
- "loss": 0.1741,
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  "step": 100
81
  },
82
  {
83
- "epoch": 0.006729475100942127,
84
- "grad_norm": 2.9103174209594727,
85
- "learning_rate": 1.1116777154513005e-06,
86
- "loss": 0.1808,
87
  "step": 110
88
  },
89
  {
90
- "epoch": 0.007341245564664138,
91
- "grad_norm": 2.3954272270202637,
92
- "learning_rate": 1.2136664966853646e-06,
93
- "loss": 0.161,
94
  "step": 120
95
  },
96
  {
97
- "epoch": 0.00795301602838615,
98
- "grad_norm": 3.030513048171997,
99
- "learning_rate": 1.3156552779194289e-06,
100
- "loss": 0.1689,
101
  "step": 130
102
  },
103
  {
104
- "epoch": 0.008564786492108161,
105
- "grad_norm": 1.7593587636947632,
106
- "learning_rate": 1.4176440591534932e-06,
107
- "loss": 0.1595,
108
  "step": 140
109
  },
110
  {
111
- "epoch": 0.009176556955830173,
112
- "grad_norm": 1.9787609577178955,
113
- "learning_rate": 1.5196328403875573e-06,
114
- "loss": 0.1429,
115
  "step": 150
116
  },
117
  {
118
- "epoch": 0.009788327419552184,
119
- "grad_norm": 2.549748659133911,
120
- "learning_rate": 1.6216216216216219e-06,
121
- "loss": 0.154,
122
  "step": 160
123
  },
124
  {
125
- "epoch": 0.010400097883274196,
126
- "grad_norm": 2.4056687355041504,
127
- "learning_rate": 1.723610402855686e-06,
128
- "loss": 0.1582,
129
  "step": 170
130
  },
131
  {
132
- "epoch": 0.011011868346996207,
133
- "grad_norm": 3.3082435131073,
134
- "learning_rate": 1.8255991840897503e-06,
135
- "loss": 0.1502,
136
  "step": 180
137
  },
138
  {
139
- "epoch": 0.011623638810718219,
140
- "grad_norm": 3.446185350418091,
141
- "learning_rate": 1.9275879653238146e-06,
142
- "loss": 0.1452,
143
  "step": 190
144
  },
145
  {
146
- "epoch": 0.01223540927444023,
147
- "grad_norm": 2.6021993160247803,
148
- "learning_rate": 2.029576746557879e-06,
149
- "loss": 0.1404,
150
  "step": 200
151
  },
152
  {
153
- "epoch": 0.012847179738162242,
154
- "grad_norm": 2.1967263221740723,
155
- "learning_rate": 2.1315655277919432e-06,
156
- "loss": 0.1421,
 
 
 
 
 
 
 
 
 
 
 
 
 
157
  "step": 210
158
  },
159
  {
160
- "epoch": 0.013458950201884253,
161
- "grad_norm": 1.9831513166427612,
162
- "learning_rate": 2.233554309026007e-06,
163
- "loss": 0.1431,
164
  "step": 220
165
  },
166
  {
167
- "epoch": 0.014070720665606265,
168
- "grad_norm": 1.7445921897888184,
169
- "learning_rate": 2.3355430902600715e-06,
170
- "loss": 0.1242,
171
  "step": 230
172
  },
173
  {
174
- "epoch": 0.014682491129328276,
175
- "grad_norm": 2.7725071907043457,
176
- "learning_rate": 2.4375318714941358e-06,
177
- "loss": 0.1346,
178
  "step": 240
179
  },
180
  {
181
- "epoch": 0.015294261593050288,
182
- "grad_norm": 1.7258802652359009,
183
- "learning_rate": 2.5395206527282e-06,
184
- "loss": 0.1371,
185
  "step": 250
186
  },
187
  {
188
- "epoch": 0.0159060320567723,
189
- "grad_norm": 2.1158506870269775,
190
- "learning_rate": 2.6415094339622644e-06,
191
- "loss": 0.1271,
192
  "step": 260
193
  },
194
  {
195
- "epoch": 0.01651780252049431,
196
- "grad_norm": 2.0771985054016113,
197
- "learning_rate": 2.7434982151963283e-06,
198
- "loss": 0.1214,
199
  "step": 270
200
  },
201
  {
202
- "epoch": 0.017129572984216322,
203
- "grad_norm": 2.924894332885742,
204
- "learning_rate": 2.8454869964303926e-06,
205
- "loss": 0.1281,
206
  "step": 280
207
  },
208
  {
209
- "epoch": 0.017741343447938332,
210
- "grad_norm": 2.122687578201294,
211
- "learning_rate": 2.947475777664457e-06,
212
- "loss": 0.132,
213
  "step": 290
214
  },
215
  {
216
- "epoch": 0.018353113911660345,
217
- "grad_norm": 3.2565481662750244,
218
- "learning_rate": 3.0494645588985217e-06,
219
- "loss": 0.1336,
220
  "step": 300
221
  },
222
  {
223
- "epoch": 0.018964884375382355,
224
- "grad_norm": 1.2805263996124268,
225
- "learning_rate": 3.151453340132586e-06,
226
- "loss": 0.1183,
 
 
 
 
 
 
 
 
 
 
 
 
 
227
  "step": 310
228
  },
229
  {
230
- "epoch": 0.019576654839104368,
231
- "grad_norm": 2.420628786087036,
232
- "learning_rate": 3.25344212136665e-06,
233
- "loss": 0.1125,
234
  "step": 320
235
  },
236
  {
237
- "epoch": 0.020188425302826378,
238
- "grad_norm": 2.887117862701416,
239
- "learning_rate": 3.3554309026007142e-06,
240
- "loss": 0.1041,
241
  "step": 330
242
  },
243
  {
244
- "epoch": 0.02080019576654839,
245
- "grad_norm": 1.6021567583084106,
246
- "learning_rate": 3.4574196838347786e-06,
247
- "loss": 0.1221,
248
  "step": 340
249
  },
250
  {
251
- "epoch": 0.0214119662302704,
252
- "grad_norm": 2.9132304191589355,
253
- "learning_rate": 3.5594084650688425e-06,
254
- "loss": 0.1094,
255
  "step": 350
256
  },
257
  {
258
- "epoch": 0.022023736693992414,
259
- "grad_norm": 2.5460691452026367,
260
- "learning_rate": 3.6613972463029068e-06,
261
- "loss": 0.1096,
262
  "step": 360
263
  },
264
  {
265
- "epoch": 0.022635507157714424,
266
- "grad_norm": 2.2170896530151367,
267
- "learning_rate": 3.763386027536971e-06,
268
- "loss": 0.0933,
269
  "step": 370
270
  },
271
  {
272
- "epoch": 0.023247277621436437,
273
- "grad_norm": 3.799591541290283,
274
- "learning_rate": 3.865374808771036e-06,
275
- "loss": 0.1142,
276
  "step": 380
277
  },
278
  {
279
- "epoch": 0.023859048085158447,
280
- "grad_norm": 4.609161376953125,
281
- "learning_rate": 3.9673635900051e-06,
282
- "loss": 0.0948,
283
  "step": 390
284
  },
285
  {
286
- "epoch": 0.02447081854888046,
287
- "grad_norm": 3.329650402069092,
288
- "learning_rate": 4.0693523712391645e-06,
289
- "loss": 0.0944,
290
  "step": 400
291
  },
292
  {
293
- "epoch": 0.02508258901260247,
294
- "grad_norm": 2.135805368423462,
295
- "learning_rate": 4.171341152473228e-06,
296
- "loss": 0.0847,
 
 
 
 
 
 
 
 
 
 
 
 
 
297
  "step": 410
298
  },
299
  {
300
- "epoch": 0.025694359476324483,
301
- "grad_norm": 2.006049156188965,
302
- "learning_rate": 4.273329933707292e-06,
303
- "loss": 0.1077,
304
  "step": 420
305
  },
306
  {
307
- "epoch": 0.026306129940046493,
308
- "grad_norm": 5.709030628204346,
309
- "learning_rate": 4.375318714941357e-06,
310
- "loss": 0.099,
311
  "step": 430
312
  },
313
  {
314
- "epoch": 0.026917900403768506,
315
- "grad_norm": 2.466867446899414,
316
- "learning_rate": 4.477307496175421e-06,
317
- "loss": 0.0771,
318
  "step": 440
319
  },
320
  {
321
- "epoch": 0.027529670867490516,
322
- "grad_norm": 2.3829548358917236,
323
- "learning_rate": 4.579296277409485e-06,
324
- "loss": 0.0802,
325
  "step": 450
326
  },
327
  {
328
- "epoch": 0.02814144133121253,
329
- "grad_norm": 2.990241050720215,
330
- "learning_rate": 4.6812850586435496e-06,
331
- "loss": 0.1048,
332
  "step": 460
333
  },
334
  {
335
- "epoch": 0.02875321179493454,
336
- "grad_norm": 3.7126529216766357,
337
- "learning_rate": 4.783273839877614e-06,
338
- "loss": 0.0879,
339
  "step": 470
340
  },
341
  {
342
- "epoch": 0.029364982258656552,
343
- "grad_norm": 2.6238865852355957,
344
- "learning_rate": 4.885262621111678e-06,
345
- "loss": 0.0825,
346
  "step": 480
347
  },
348
  {
349
- "epoch": 0.029976752722378562,
350
- "grad_norm": 2.1882681846618652,
351
- "learning_rate": 4.987251402345742e-06,
352
- "loss": 0.0821,
353
  "step": 490
354
  },
355
  {
356
- "epoch": 0.030588523186100575,
357
- "grad_norm": 2.1399929523468018,
358
- "learning_rate": 5.089240183579807e-06,
359
- "loss": 0.0926,
360
  "step": 500
361
  },
362
  {
363
- "epoch": 0.030588523186100575,
364
- "eval_accuracy": 0.8732,
365
- "eval_f1_weighted": 0.8728301347090768,
366
- "eval_loss": 0.08081420511007309,
367
- "eval_macro_f1": 0.8730387325792941,
368
- "eval_precision": 0.8842823474890878,
369
- "eval_recall": 0.8732,
370
- "eval_runtime": 1731.362,
371
- "eval_samples_per_second": 57.758,
372
- "eval_steps_per_second": 0.903,
373
  "step": 500
374
  },
375
  {
376
- "epoch": 0.031200293649822585,
377
- "grad_norm": 4.9644694328308105,
378
- "learning_rate": 5.191228964813872e-06,
379
- "loss": 0.0846,
380
  "step": 510
381
  },
382
  {
383
- "epoch": 0.0318120641135446,
384
- "grad_norm": 3.2999346256256104,
385
- "learning_rate": 5.293217746047935e-06,
386
- "loss": 0.0774,
387
  "step": 520
388
  },
389
  {
390
- "epoch": 0.03242383457726661,
391
- "grad_norm": 1.9823625087738037,
392
- "learning_rate": 5.395206527281999e-06,
393
- "loss": 0.0781,
394
  "step": 530
395
  },
396
  {
397
- "epoch": 0.03303560504098862,
398
- "grad_norm": 2.010012149810791,
399
- "learning_rate": 5.497195308516063e-06,
400
- "loss": 0.0748,
401
  "step": 540
402
  },
403
  {
404
- "epoch": 0.033647375504710635,
405
- "grad_norm": 1.7753310203552246,
406
- "learning_rate": 5.599184089750128e-06,
407
- "loss": 0.0687,
408
  "step": 550
409
  },
410
  {
411
- "epoch": 0.034259145968432644,
412
- "grad_norm": 1.4343310594558716,
413
- "learning_rate": 5.701172870984192e-06,
414
- "loss": 0.0729,
415
  "step": 560
416
  },
417
  {
418
- "epoch": 0.034870916432154654,
419
- "grad_norm": 2.562145948410034,
420
- "learning_rate": 5.803161652218257e-06,
421
- "loss": 0.0712,
422
  "step": 570
423
  },
424
  {
425
- "epoch": 0.035482686895876664,
426
- "grad_norm": 1.727373480796814,
427
- "learning_rate": 5.9051504334523206e-06,
428
- "loss": 0.0605,
429
  "step": 580
430
  },
431
  {
432
- "epoch": 0.03609445735959868,
433
- "grad_norm": 1.8711422681808472,
434
- "learning_rate": 6.007139214686385e-06,
435
- "loss": 0.071,
436
  "step": 590
437
  },
438
  {
439
- "epoch": 0.03670622782332069,
440
- "grad_norm": 7.535566329956055,
441
- "learning_rate": 6.10912799592045e-06,
442
- "loss": 0.067,
443
  "step": 600
444
  },
445
  {
446
- "epoch": 0.0373179982870427,
447
- "grad_norm": 3.9871439933776855,
448
- "learning_rate": 6.211116777154513e-06,
449
- "loss": 0.063,
 
 
 
 
 
 
 
 
 
 
 
 
 
450
  "step": 610
451
  },
452
  {
453
- "epoch": 0.03792976875076471,
454
- "grad_norm": 2.457789659500122,
455
- "learning_rate": 6.313105558388578e-06,
456
- "loss": 0.0905,
457
  "step": 620
458
  },
459
  {
460
- "epoch": 0.03854153921448673,
461
- "grad_norm": 4.795208930969238,
462
- "learning_rate": 6.415094339622642e-06,
463
- "loss": 0.0611,
464
  "step": 630
465
  },
466
  {
467
- "epoch": 0.039153309678208736,
468
- "grad_norm": 3.688422441482544,
469
- "learning_rate": 6.5170831208567065e-06,
470
- "loss": 0.0657,
471
  "step": 640
472
  },
473
  {
474
- "epoch": 0.039765080141930746,
475
- "grad_norm": 4.9787116050720215,
476
- "learning_rate": 6.61907190209077e-06,
477
- "loss": 0.0593,
478
  "step": 650
479
  },
480
  {
481
- "epoch": 0.040376850605652756,
482
- "grad_norm": 6.09706974029541,
483
- "learning_rate": 6.721060683324835e-06,
484
- "loss": 0.0803,
485
  "step": 660
486
  },
487
  {
488
- "epoch": 0.04098862106937477,
489
- "grad_norm": 1.9047552347183228,
490
- "learning_rate": 6.8230494645589e-06,
491
- "loss": 0.0486,
492
  "step": 670
493
  },
494
  {
495
- "epoch": 0.04160039153309678,
496
- "grad_norm": 3.514389753341675,
497
- "learning_rate": 6.925038245792963e-06,
498
- "loss": 0.058,
499
  "step": 680
500
  },
501
  {
502
- "epoch": 0.04221216199681879,
503
- "grad_norm": 3.366957187652588,
504
- "learning_rate": 7.027027027027028e-06,
505
- "loss": 0.0651,
506
  "step": 690
507
  },
508
  {
509
- "epoch": 0.0428239324605408,
510
- "grad_norm": 4.780582904815674,
511
- "learning_rate": 7.1290158082610916e-06,
512
- "loss": 0.0561,
 
 
 
 
 
 
 
 
 
 
 
 
 
513
  "step": 700
514
  },
515
  {
516
- "epoch": 0.04343570292426282,
517
- "grad_norm": 2.457082748413086,
518
- "learning_rate": 7.231004589495156e-06,
519
- "loss": 0.0611,
520
  "step": 710
521
  },
522
  {
523
- "epoch": 0.04404747338798483,
524
- "grad_norm": 1.283014178276062,
525
- "learning_rate": 7.33299337072922e-06,
526
- "loss": 0.0601,
527
  "step": 720
528
  },
529
  {
530
- "epoch": 0.04465924385170684,
531
- "grad_norm": 3.092107057571411,
532
- "learning_rate": 7.434982151963285e-06,
533
- "loss": 0.0598,
534
  "step": 730
535
  },
536
  {
537
- "epoch": 0.04527101431542885,
538
- "grad_norm": 1.26460599899292,
539
- "learning_rate": 7.536970933197348e-06,
540
- "loss": 0.0503,
541
  "step": 740
542
  },
543
  {
544
- "epoch": 0.045882784779150865,
545
- "grad_norm": 2.9157862663269043,
546
- "learning_rate": 7.638959714431414e-06,
547
- "loss": 0.0507,
548
  "step": 750
549
  },
550
  {
551
- "epoch": 0.046494555242872875,
552
- "grad_norm": 5.487971782684326,
553
- "learning_rate": 7.740948495665478e-06,
554
- "loss": 0.0525,
555
  "step": 760
556
  },
557
  {
558
- "epoch": 0.047106325706594884,
559
- "grad_norm": 2.9894769191741943,
560
- "learning_rate": 7.842937276899541e-06,
561
- "loss": 0.0656,
562
  "step": 770
563
  },
564
  {
565
- "epoch": 0.047718096170316894,
566
- "grad_norm": 2.7786455154418945,
567
- "learning_rate": 7.944926058133606e-06,
568
- "loss": 0.0521,
569
  "step": 780
570
  },
571
  {
572
- "epoch": 0.04832986663403891,
573
- "grad_norm": 1.3629153966903687,
574
- "learning_rate": 8.04691483936767e-06,
575
- "loss": 0.0529,
576
  "step": 790
577
  },
578
  {
579
- "epoch": 0.04894163709776092,
580
- "grad_norm": 4.066152572631836,
581
- "learning_rate": 8.148903620601734e-06,
582
- "loss": 0.047,
583
  "step": 800
584
  },
585
  {
586
- "epoch": 0.04955340756148293,
587
- "grad_norm": 2.162338972091675,
588
- "learning_rate": 8.250892401835799e-06,
589
- "loss": 0.0583,
 
 
 
 
 
 
 
 
 
 
 
 
 
590
  "step": 810
591
  },
592
  {
593
- "epoch": 0.05016517802520494,
594
- "grad_norm": 1.5794885158538818,
595
- "learning_rate": 8.352881183069863e-06,
596
- "loss": 0.0415,
597
  "step": 820
598
  },
599
  {
600
- "epoch": 0.05077694848892696,
601
- "grad_norm": 5.697793960571289,
602
- "learning_rate": 8.454869964303928e-06,
603
- "loss": 0.0614,
604
  "step": 830
605
  },
606
  {
607
- "epoch": 0.05138871895264897,
608
- "grad_norm": 2.243929386138916,
609
- "learning_rate": 8.556858745537991e-06,
610
- "loss": 0.0836,
611
  "step": 840
612
  },
613
  {
614
- "epoch": 0.052000489416370976,
615
- "grad_norm": 1.272515892982483,
616
- "learning_rate": 8.658847526772056e-06,
617
- "loss": 0.05,
618
  "step": 850
619
  },
620
  {
621
- "epoch": 0.052612259880092986,
622
- "grad_norm": 1.4770886898040771,
623
- "learning_rate": 8.760836308006119e-06,
624
- "loss": 0.0403,
625
  "step": 860
626
  },
627
  {
628
- "epoch": 0.053224030343815,
629
- "grad_norm": 3.411848306655884,
630
- "learning_rate": 8.862825089240184e-06,
631
- "loss": 0.0478,
632
  "step": 870
633
  },
634
  {
635
- "epoch": 0.05383580080753701,
636
- "grad_norm": 8.478028297424316,
637
- "learning_rate": 8.964813870474248e-06,
638
- "loss": 0.0855,
639
  "step": 880
640
  },
641
  {
642
- "epoch": 0.05444757127125902,
643
- "grad_norm": 0.6067395806312561,
644
- "learning_rate": 9.066802651708313e-06,
645
- "loss": 0.0366,
646
  "step": 890
647
  },
648
  {
649
- "epoch": 0.05505934173498103,
650
- "grad_norm": 2.6501152515411377,
651
- "learning_rate": 9.168791432942376e-06,
652
- "loss": 0.0358,
 
 
 
 
 
 
 
 
 
 
 
 
 
653
  "step": 900
654
  },
655
  {
656
- "epoch": 0.05567111219870305,
657
- "grad_norm": 1.1650569438934326,
658
- "learning_rate": 9.270780214176441e-06,
659
- "loss": 0.0733,
660
  "step": 910
661
  },
662
  {
663
- "epoch": 0.05628288266242506,
664
- "grad_norm": 2.4513559341430664,
665
- "learning_rate": 9.372768995410506e-06,
666
- "loss": 0.0535,
667
  "step": 920
668
  },
669
  {
670
- "epoch": 0.05689465312614707,
671
- "grad_norm": 0.8360533714294434,
672
- "learning_rate": 9.47475777664457e-06,
673
- "loss": 0.0453,
674
  "step": 930
675
  },
676
  {
677
- "epoch": 0.05750642358986908,
678
- "grad_norm": 2.2937448024749756,
679
- "learning_rate": 9.576746557878635e-06,
680
- "loss": 0.0655,
681
  "step": 940
682
  },
683
  {
684
- "epoch": 0.058118194053591095,
685
- "grad_norm": 2.025761127471924,
686
- "learning_rate": 9.678735339112698e-06,
687
- "loss": 0.06,
688
  "step": 950
689
  },
690
  {
691
- "epoch": 0.058729964517313105,
692
- "grad_norm": 2.6468706130981445,
693
- "learning_rate": 9.780724120346763e-06,
694
- "loss": 0.0416,
695
  "step": 960
696
  },
697
  {
698
- "epoch": 0.059341734981035114,
699
- "grad_norm": 3.626215934753418,
700
- "learning_rate": 9.882712901580826e-06,
701
- "loss": 0.0239,
702
  "step": 970
703
  },
704
  {
705
- "epoch": 0.059953505444757124,
706
- "grad_norm": 2.599356174468994,
707
- "learning_rate": 9.984701682814891e-06,
708
- "loss": 0.0395,
709
  "step": 980
710
  },
711
  {
712
- "epoch": 0.06056527590847914,
713
- "grad_norm": 2.4896769523620605,
714
- "learning_rate": 1.0086690464048956e-05,
715
- "loss": 0.0703,
716
  "step": 990
717
  },
718
  {
719
- "epoch": 0.06117704637220115,
720
- "grad_norm": 2.18449068069458,
721
- "learning_rate": 1.018867924528302e-05,
722
- "loss": 0.0306,
723
  "step": 1000
724
  },
725
  {
726
- "epoch": 0.06117704637220115,
727
- "eval_accuracy": 0.95488,
728
- "eval_f1_weighted": 0.9549029721025599,
729
- "eval_loss": 0.03926030173897743,
730
- "eval_macro_f1": 0.9548451024890077,
731
- "eval_precision": 0.955565530093091,
732
- "eval_recall": 0.95488,
733
- "eval_runtime": 1718.0831,
734
- "eval_samples_per_second": 58.204,
735
- "eval_steps_per_second": 0.91,
736
  "step": 1000
737
  }
738
  ],
739
  "logging_steps": 10,
740
- "max_steps": 16346,
741
  "num_input_tokens_seen": 0,
742
  "num_train_epochs": 1,
743
- "save_steps": 500,
744
  "stateful_callbacks": {
745
  "EarlyStoppingCallback": {
746
  "args": {
@@ -762,8 +866,8 @@
762
  "attributes": {}
763
  }
764
  },
765
- "total_flos": 8415771550099200.0,
766
- "train_batch_size": 32,
767
  "trial_name": null,
768
  "trial_params": null
769
  }
 
1
  {
2
  "best_global_step": 1000,
3
+ "best_metric": 0.9644889377060355,
4
  "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1000",
5
+ "epoch": 0.1223540927444023,
6
+ "eval_steps": 100,
7
  "global_step": 1000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.001223540927444023,
14
+ "grad_norm": 0.1898110806941986,
15
+ "learning_rate": 3.6734693877551025e-07,
16
+ "loss": 0.4422,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.002447081854888046,
21
+ "grad_norm": 0.3350900411605835,
22
+ "learning_rate": 7.346938775510205e-07,
23
+ "loss": 0.4323,
24
  "step": 20
25
  },
26
  {
27
+ "epoch": 0.003670622782332069,
28
+ "grad_norm": 0.3723449110984802,
29
+ "learning_rate": 1.142857142857143e-06,
30
+ "loss": 0.4362,
31
  "step": 30
32
  },
33
  {
34
+ "epoch": 0.004894163709776092,
35
+ "grad_norm": 0.3299769461154938,
36
+ "learning_rate": 1.5510204081632654e-06,
37
+ "loss": 0.4191,
38
  "step": 40
39
  },
40
  {
41
+ "epoch": 0.006117704637220115,
42
+ "grad_norm": 0.26681044697761536,
43
+ "learning_rate": 1.9591836734693877e-06,
44
+ "loss": 0.4289,
45
  "step": 50
46
  },
47
  {
48
+ "epoch": 0.007341245564664138,
49
+ "grad_norm": 0.30233338475227356,
50
+ "learning_rate": 2.3673469387755103e-06,
51
+ "loss": 0.4083,
52
  "step": 60
53
  },
54
  {
55
+ "epoch": 0.008564786492108161,
56
+ "grad_norm": 0.31031334400177,
57
+ "learning_rate": 2.775510204081633e-06,
58
+ "loss": 0.404,
59
  "step": 70
60
  },
61
  {
62
+ "epoch": 0.009788327419552184,
63
+ "grad_norm": 0.2552475035190582,
64
+ "learning_rate": 3.183673469387755e-06,
65
+ "loss": 0.3889,
66
  "step": 80
67
  },
68
  {
69
+ "epoch": 0.011011868346996207,
70
+ "grad_norm": 0.3131052553653717,
71
+ "learning_rate": 3.5918367346938777e-06,
72
+ "loss": 0.3813,
73
  "step": 90
74
  },
75
  {
76
+ "epoch": 0.01223540927444023,
77
+ "grad_norm": 0.3377229571342468,
78
+ "learning_rate": 4.000000000000001e-06,
79
+ "loss": 0.3727,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.01223540927444023,
84
+ "eval_accuracy": 0.6961,
85
+ "eval_f1_weighted": 0.6955947095331424,
86
+ "eval_loss": 0.15026023983955383,
87
+ "eval_macro_f1": 0.6959280508399847,
88
+ "eval_precision": 0.7019396279846728,
89
+ "eval_recall": 0.6961,
90
+ "eval_runtime": 789.7648,
91
+ "eval_samples_per_second": 126.62,
92
+ "eval_steps_per_second": 0.99,
93
  "step": 100
94
  },
95
  {
96
+ "epoch": 0.013458950201884253,
97
+ "grad_norm": 0.3366774618625641,
98
+ "learning_rate": 4.408163265306123e-06,
99
+ "loss": 0.3671,
100
  "step": 110
101
  },
102
  {
103
+ "epoch": 0.014682491129328276,
104
+ "grad_norm": 0.33491575717926025,
105
+ "learning_rate": 4.816326530612245e-06,
106
+ "loss": 0.3498,
107
  "step": 120
108
  },
109
  {
110
+ "epoch": 0.0159060320567723,
111
+ "grad_norm": 0.4119006097316742,
112
+ "learning_rate": 5.2244897959183684e-06,
113
+ "loss": 0.3409,
114
  "step": 130
115
  },
116
  {
117
+ "epoch": 0.017129572984216322,
118
+ "grad_norm": 0.2964725196361542,
119
+ "learning_rate": 5.63265306122449e-06,
120
+ "loss": 0.3433,
121
  "step": 140
122
  },
123
  {
124
+ "epoch": 0.018353113911660345,
125
+ "grad_norm": 0.3075334429740906,
126
+ "learning_rate": 6.040816326530613e-06,
127
+ "loss": 0.3298,
128
  "step": 150
129
  },
130
  {
131
+ "epoch": 0.019576654839104368,
132
+ "grad_norm": 0.33718687295913696,
133
+ "learning_rate": 6.4489795918367345e-06,
134
+ "loss": 0.3297,
135
  "step": 160
136
  },
137
  {
138
+ "epoch": 0.02080019576654839,
139
+ "grad_norm": 0.2809618413448334,
140
+ "learning_rate": 6.857142857142858e-06,
141
+ "loss": 0.3275,
142
  "step": 170
143
  },
144
  {
145
+ "epoch": 0.022023736693992414,
146
+ "grad_norm": 0.37805014848709106,
147
+ "learning_rate": 7.2653061224489805e-06,
148
+ "loss": 0.3201,
149
  "step": 180
150
  },
151
  {
152
+ "epoch": 0.023247277621436437,
153
+ "grad_norm": 0.2940429151058197,
154
+ "learning_rate": 7.673469387755102e-06,
155
+ "loss": 0.3042,
156
  "step": 190
157
  },
158
  {
159
+ "epoch": 0.02447081854888046,
160
+ "grad_norm": 0.3286060690879822,
161
+ "learning_rate": 8.081632653061225e-06,
162
+ "loss": 0.3071,
163
  "step": 200
164
  },
165
  {
166
+ "epoch": 0.02447081854888046,
167
+ "eval_accuracy": 0.77807,
168
+ "eval_f1_weighted": 0.7781129395311969,
169
+ "eval_loss": 0.12153773754835129,
170
+ "eval_macro_f1": 0.7780651598452646,
171
+ "eval_precision": 0.7808306361972198,
172
+ "eval_recall": 0.77807,
173
+ "eval_runtime": 792.7157,
174
+ "eval_samples_per_second": 126.149,
175
+ "eval_steps_per_second": 0.986,
176
+ "step": 200
177
+ },
178
+ {
179
+ "epoch": 0.025694359476324483,
180
+ "grad_norm": 0.33857154846191406,
181
+ "learning_rate": 8.489795918367347e-06,
182
+ "loss": 0.2964,
183
  "step": 210
184
  },
185
  {
186
+ "epoch": 0.026917900403768506,
187
+ "grad_norm": 0.2752092182636261,
188
+ "learning_rate": 8.89795918367347e-06,
189
+ "loss": 0.3,
190
  "step": 220
191
  },
192
  {
193
+ "epoch": 0.02814144133121253,
194
+ "grad_norm": 0.4952544569969177,
195
+ "learning_rate": 9.306122448979593e-06,
196
+ "loss": 0.294,
197
  "step": 230
198
  },
199
  {
200
+ "epoch": 0.029364982258656552,
201
+ "grad_norm": 0.37926042079925537,
202
+ "learning_rate": 9.714285714285715e-06,
203
+ "loss": 0.2964,
204
  "step": 240
205
  },
206
  {
207
+ "epoch": 0.030588523186100575,
208
+ "grad_norm": 0.3222455680370331,
209
+ "learning_rate": 1.0122448979591836e-05,
210
+ "loss": 0.283,
211
  "step": 250
212
  },
213
  {
214
+ "epoch": 0.0318120641135446,
215
+ "grad_norm": 0.2930658459663391,
216
+ "learning_rate": 1.053061224489796e-05,
217
+ "loss": 0.2793,
218
  "step": 260
219
  },
220
  {
221
+ "epoch": 0.03303560504098862,
222
+ "grad_norm": 0.4313414692878723,
223
+ "learning_rate": 1.0938775510204083e-05,
224
+ "loss": 0.2728,
225
  "step": 270
226
  },
227
  {
228
+ "epoch": 0.034259145968432644,
229
+ "grad_norm": 0.37351569533348083,
230
+ "learning_rate": 1.1346938775510206e-05,
231
+ "loss": 0.2752,
232
  "step": 280
233
  },
234
  {
235
+ "epoch": 0.035482686895876664,
236
+ "grad_norm": 0.22772285342216492,
237
+ "learning_rate": 1.1755102040816328e-05,
238
+ "loss": 0.274,
239
  "step": 290
240
  },
241
  {
242
+ "epoch": 0.03670622782332069,
243
+ "grad_norm": 0.15888753533363342,
244
+ "learning_rate": 1.2163265306122449e-05,
245
+ "loss": 0.264,
246
  "step": 300
247
  },
248
  {
249
+ "epoch": 0.03670622782332069,
250
+ "eval_accuracy": 0.82326,
251
+ "eval_f1_weighted": 0.8227034206790359,
252
+ "eval_loss": 0.10234300792217255,
253
+ "eval_macro_f1": 0.8230100448030374,
254
+ "eval_precision": 0.8338333810964687,
255
+ "eval_recall": 0.82326,
256
+ "eval_runtime": 789.0168,
257
+ "eval_samples_per_second": 126.74,
258
+ "eval_steps_per_second": 0.991,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.03792976875076471,
263
+ "grad_norm": 0.23560188710689545,
264
+ "learning_rate": 1.2571428571428572e-05,
265
+ "loss": 0.2753,
266
  "step": 310
267
  },
268
  {
269
+ "epoch": 0.039153309678208736,
270
+ "grad_norm": 0.18699614703655243,
271
+ "learning_rate": 1.2979591836734696e-05,
272
+ "loss": 0.2565,
273
  "step": 320
274
  },
275
  {
276
+ "epoch": 0.040376850605652756,
277
+ "grad_norm": 0.24035991728305817,
278
+ "learning_rate": 1.3387755102040818e-05,
279
+ "loss": 0.2716,
280
  "step": 330
281
  },
282
  {
283
+ "epoch": 0.04160039153309678,
284
+ "grad_norm": 0.15309660136699677,
285
+ "learning_rate": 1.3795918367346941e-05,
286
+ "loss": 0.2515,
287
  "step": 340
288
  },
289
  {
290
+ "epoch": 0.0428239324605408,
291
+ "grad_norm": 0.3382055461406708,
292
+ "learning_rate": 1.4204081632653062e-05,
293
+ "loss": 0.2597,
294
  "step": 350
295
  },
296
  {
297
+ "epoch": 0.04404747338798483,
298
+ "grad_norm": 0.24439455568790436,
299
+ "learning_rate": 1.4612244897959185e-05,
300
+ "loss": 0.247,
301
  "step": 360
302
  },
303
  {
304
+ "epoch": 0.04527101431542885,
305
+ "grad_norm": 0.26233720779418945,
306
+ "learning_rate": 1.5020408163265307e-05,
307
+ "loss": 0.2431,
308
  "step": 370
309
  },
310
  {
311
+ "epoch": 0.046494555242872875,
312
+ "grad_norm": 0.20477451384067535,
313
+ "learning_rate": 1.5387755102040818e-05,
314
+ "loss": 0.2538,
315
  "step": 380
316
  },
317
  {
318
+ "epoch": 0.047718096170316894,
319
+ "grad_norm": 0.2765439748764038,
320
+ "learning_rate": 1.5795918367346942e-05,
321
+ "loss": 0.2404,
322
  "step": 390
323
  },
324
  {
325
+ "epoch": 0.04894163709776092,
326
+ "grad_norm": 0.13196279108524323,
327
+ "learning_rate": 1.6204081632653063e-05,
328
+ "loss": 0.2393,
329
  "step": 400
330
  },
331
  {
332
+ "epoch": 0.04894163709776092,
333
+ "eval_accuracy": 0.84563,
334
+ "eval_f1_weighted": 0.8448128964509274,
335
+ "eval_loss": 0.09028046578168869,
336
+ "eval_macro_f1": 0.8451923512067675,
337
+ "eval_precision": 0.861024732271907,
338
+ "eval_recall": 0.84563,
339
+ "eval_runtime": 787.6067,
340
+ "eval_samples_per_second": 126.967,
341
+ "eval_steps_per_second": 0.993,
342
+ "step": 400
343
+ },
344
+ {
345
+ "epoch": 0.05016517802520494,
346
+ "grad_norm": 0.0924634337425232,
347
+ "learning_rate": 1.6612244897959184e-05,
348
+ "loss": 0.2331,
349
  "step": 410
350
  },
351
  {
352
+ "epoch": 0.05138871895264897,
353
+ "grad_norm": 0.277784138917923,
354
+ "learning_rate": 1.7020408163265308e-05,
355
+ "loss": 0.2301,
356
  "step": 420
357
  },
358
  {
359
+ "epoch": 0.052612259880092986,
360
+ "grad_norm": 0.32299959659576416,
361
+ "learning_rate": 1.742857142857143e-05,
362
+ "loss": 0.2218,
363
  "step": 430
364
  },
365
  {
366
+ "epoch": 0.05383580080753701,
367
+ "grad_norm": 0.18170586228370667,
368
+ "learning_rate": 1.7836734693877553e-05,
369
+ "loss": 0.2318,
370
  "step": 440
371
  },
372
  {
373
+ "epoch": 0.05505934173498103,
374
+ "grad_norm": 0.1520216166973114,
375
+ "learning_rate": 1.8244897959183674e-05,
376
+ "loss": 0.2136,
377
  "step": 450
378
  },
379
  {
380
+ "epoch": 0.05628288266242506,
381
+ "grad_norm": 0.23452645540237427,
382
+ "learning_rate": 1.8653061224489795e-05,
383
+ "loss": 0.2219,
384
  "step": 460
385
  },
386
  {
387
+ "epoch": 0.05750642358986908,
388
+ "grad_norm": 0.10036301612854004,
389
+ "learning_rate": 1.906122448979592e-05,
390
+ "loss": 0.2213,
391
  "step": 470
392
  },
393
  {
394
+ "epoch": 0.058729964517313105,
395
+ "grad_norm": 0.24100220203399658,
396
+ "learning_rate": 1.9469387755102044e-05,
397
+ "loss": 0.2079,
398
  "step": 480
399
  },
400
  {
401
+ "epoch": 0.059953505444757124,
402
+ "grad_norm": 0.28893032670021057,
403
+ "learning_rate": 1.9877551020408165e-05,
404
+ "loss": 0.1978,
405
  "step": 490
406
  },
407
  {
408
+ "epoch": 0.06117704637220115,
409
+ "grad_norm": 0.22918537259101868,
410
+ "learning_rate": 1.9999836143766126e-05,
411
+ "loss": 0.202,
412
  "step": 500
413
  },
414
  {
415
+ "epoch": 0.06117704637220115,
416
+ "eval_accuracy": 0.91628,
417
+ "eval_f1_weighted": 0.9163231793856368,
418
+ "eval_loss": 0.055908624082803726,
419
+ "eval_macro_f1": 0.9162187423616152,
420
+ "eval_precision": 0.9170320825159874,
421
+ "eval_recall": 0.91628,
422
+ "eval_runtime": 760.1138,
423
+ "eval_samples_per_second": 131.559,
424
+ "eval_steps_per_second": 1.029,
425
  "step": 500
426
  },
427
  {
428
+ "epoch": 0.06240058729964517,
429
+ "grad_norm": 0.2930404841899872,
430
+ "learning_rate": 1.999903359554741e-05,
431
+ "loss": 0.1979,
432
  "step": 510
433
  },
434
  {
435
+ "epoch": 0.0636241282270892,
436
+ "grad_norm": 0.0889664739370346,
437
+ "learning_rate": 1.9997562312908153e-05,
438
+ "loss": 0.1953,
439
  "step": 520
440
  },
441
  {
442
+ "epoch": 0.06484766915453322,
443
+ "grad_norm": 0.1687588095664978,
444
+ "learning_rate": 1.9995422394247598e-05,
445
+ "loss": 0.1935,
446
  "step": 530
447
  },
448
  {
449
+ "epoch": 0.06607121008197724,
450
+ "grad_norm": 0.2399725466966629,
451
+ "learning_rate": 1.9992613982683296e-05,
452
+ "loss": 0.1818,
453
  "step": 540
454
  },
455
  {
456
+ "epoch": 0.06729475100942127,
457
+ "grad_norm": 0.2016785889863968,
458
+ "learning_rate": 1.9989137266041552e-05,
459
+ "loss": 0.1893,
460
  "step": 550
461
  },
462
  {
463
+ "epoch": 0.06851829193686529,
464
+ "grad_norm": 0.17420713603496552,
465
+ "learning_rate": 1.9984992476844845e-05,
466
+ "loss": 0.1895,
467
  "step": 560
468
  },
469
  {
470
+ "epoch": 0.06974183286430931,
471
+ "grad_norm": 0.2180609554052353,
472
+ "learning_rate": 1.998017989229629e-05,
473
+ "loss": 0.1836,
474
  "step": 570
475
  },
476
  {
477
+ "epoch": 0.07096537379175333,
478
+ "grad_norm": 0.15563039481639862,
479
+ "learning_rate": 1.9974699834261074e-05,
480
+ "loss": 0.182,
481
  "step": 580
482
  },
483
  {
484
+ "epoch": 0.07218891471919736,
485
+ "grad_norm": 0.25410088896751404,
486
+ "learning_rate": 1.996855266924497e-05,
487
+ "loss": 0.1862,
488
  "step": 590
489
  },
490
  {
491
+ "epoch": 0.07341245564664138,
492
+ "grad_norm": 0.24206259846687317,
493
+ "learning_rate": 1.996173880836979e-05,
494
+ "loss": 0.1818,
495
  "step": 600
496
  },
497
  {
498
+ "epoch": 0.07341245564664138,
499
+ "eval_accuracy": 0.91633,
500
+ "eval_f1_weighted": 0.9162437523349878,
501
+ "eval_loss": 0.05625538155436516,
502
+ "eval_macro_f1": 0.9163072974421806,
503
+ "eval_precision": 0.9233764457540103,
504
+ "eval_recall": 0.91633,
505
+ "eval_runtime": 759.6815,
506
+ "eval_samples_per_second": 131.634,
507
+ "eval_steps_per_second": 1.029,
508
+ "step": 600
509
+ },
510
+ {
511
+ "epoch": 0.0746359965740854,
512
+ "grad_norm": 0.27251410484313965,
513
+ "learning_rate": 1.9954258707345903e-05,
514
+ "loss": 0.1845,
515
  "step": 610
516
  },
517
  {
518
+ "epoch": 0.07585953750152942,
519
+ "grad_norm": 0.1545839011669159,
520
+ "learning_rate": 1.9946112866441757e-05,
521
+ "loss": 0.1861,
522
  "step": 620
523
  },
524
  {
525
+ "epoch": 0.07708307842897345,
526
+ "grad_norm": 0.2535873055458069,
527
+ "learning_rate": 1.9937301830450423e-05,
528
+ "loss": 0.1772,
529
  "step": 630
530
  },
531
  {
532
+ "epoch": 0.07830661935641747,
533
+ "grad_norm": 0.2617948651313782,
534
+ "learning_rate": 1.992782618865315e-05,
535
+ "loss": 0.1711,
536
  "step": 640
537
  },
538
  {
539
+ "epoch": 0.07953016028386149,
540
+ "grad_norm": 0.38676971197128296,
541
+ "learning_rate": 1.9917686574779972e-05,
542
+ "loss": 0.1748,
543
  "step": 650
544
  },
545
  {
546
+ "epoch": 0.08075370121130551,
547
+ "grad_norm": 0.1511957049369812,
548
+ "learning_rate": 1.9906883666967296e-05,
549
+ "loss": 0.1825,
550
  "step": 660
551
  },
552
  {
553
+ "epoch": 0.08197724213874955,
554
+ "grad_norm": 0.2525976002216339,
555
+ "learning_rate": 1.989541818771258e-05,
556
+ "loss": 0.1651,
557
  "step": 670
558
  },
559
  {
560
+ "epoch": 0.08320078306619356,
561
+ "grad_norm": 0.25827622413635254,
562
+ "learning_rate": 1.9883290903825994e-05,
563
+ "loss": 0.1763,
564
  "step": 680
565
  },
566
  {
567
+ "epoch": 0.08442432399363758,
568
+ "grad_norm": 0.24877820909023285,
569
+ "learning_rate": 1.9870502626379127e-05,
570
+ "loss": 0.1652,
571
  "step": 690
572
  },
573
  {
574
+ "epoch": 0.0856478649210816,
575
+ "grad_norm": 0.278772234916687,
576
+ "learning_rate": 1.9857054210650776e-05,
577
+ "loss": 0.1651,
578
+ "step": 700
579
+ },
580
+ {
581
+ "epoch": 0.0856478649210816,
582
+ "eval_accuracy": 0.94905,
583
+ "eval_f1_weighted": 0.9490731118481598,
584
+ "eval_loss": 0.03884471580386162,
585
+ "eval_macro_f1": 0.9489981325237288,
586
+ "eval_precision": 0.9494795831024372,
587
+ "eval_recall": 0.94905,
588
+ "eval_runtime": 759.9337,
589
+ "eval_samples_per_second": 131.59,
590
+ "eval_steps_per_second": 1.029,
591
  "step": 700
592
  },
593
  {
594
+ "epoch": 0.08687140584852564,
595
+ "grad_norm": 0.1895805150270462,
596
+ "learning_rate": 1.9842946556069705e-05,
597
+ "loss": 0.1628,
598
  "step": 710
599
  },
600
  {
601
+ "epoch": 0.08809494677596966,
602
+ "grad_norm": 0.1171497106552124,
603
+ "learning_rate": 1.982818060615452e-05,
604
+ "loss": 0.1715,
605
  "step": 720
606
  },
607
  {
608
+ "epoch": 0.08931848770341368,
609
+ "grad_norm": 0.22032728791236877,
610
+ "learning_rate": 1.9812757348450547e-05,
611
+ "loss": 0.1712,
612
  "step": 730
613
  },
614
  {
615
+ "epoch": 0.0905420286308577,
616
+ "grad_norm": 0.20700488984584808,
617
+ "learning_rate": 1.9796677814463812e-05,
618
+ "loss": 0.1638,
619
  "step": 740
620
  },
621
  {
622
+ "epoch": 0.09176556955830173,
623
+ "grad_norm": 0.24688613414764404,
624
+ "learning_rate": 1.977994307959202e-05,
625
+ "loss": 0.1647,
626
  "step": 750
627
  },
628
  {
629
+ "epoch": 0.09298911048574575,
630
+ "grad_norm": 0.1886432021856308,
631
+ "learning_rate": 1.9762554263052655e-05,
632
+ "loss": 0.1734,
633
  "step": 760
634
  },
635
  {
636
+ "epoch": 0.09421265141318977,
637
+ "grad_norm": 0.08407370001077652,
638
+ "learning_rate": 1.9744512527808127e-05,
639
+ "loss": 0.1755,
640
  "step": 770
641
  },
642
  {
643
+ "epoch": 0.09543619234063379,
644
+ "grad_norm": 0.14160771667957306,
645
+ "learning_rate": 1.9725819080487976e-05,
646
+ "loss": 0.1749,
647
  "step": 780
648
  },
649
  {
650
+ "epoch": 0.09665973326807782,
651
+ "grad_norm": 0.17038081586360931,
652
+ "learning_rate": 1.970647517130819e-05,
653
+ "loss": 0.1795,
654
  "step": 790
655
  },
656
  {
657
+ "epoch": 0.09788327419552184,
658
+ "grad_norm": 0.24339532852172852,
659
+ "learning_rate": 1.968648209398759e-05,
660
+ "loss": 0.161,
661
  "step": 800
662
  },
663
  {
664
+ "epoch": 0.09788327419552184,
665
+ "eval_accuracy": 0.95721,
666
+ "eval_f1_weighted": 0.9572295598206603,
667
+ "eval_loss": 0.03337462991476059,
668
+ "eval_macro_f1": 0.9571669846830866,
669
+ "eval_precision": 0.9576467364395861,
670
+ "eval_recall": 0.95721,
671
+ "eval_runtime": 759.9975,
672
+ "eval_samples_per_second": 131.579,
673
+ "eval_steps_per_second": 1.029,
674
+ "step": 800
675
+ },
676
+ {
677
+ "epoch": 0.09910681512296586,
678
+ "grad_norm": 0.16346058249473572,
679
+ "learning_rate": 1.9665841185661283e-05,
680
+ "loss": 0.1596,
681
  "step": 810
682
  },
683
  {
684
+ "epoch": 0.10033035605040988,
685
+ "grad_norm": 0.25031423568725586,
686
+ "learning_rate": 1.964455382679128e-05,
687
+ "loss": 0.1662,
688
  "step": 820
689
  },
690
  {
691
+ "epoch": 0.10155389697785391,
692
+ "grad_norm": 0.36678382754325867,
693
+ "learning_rate": 1.9622621441074113e-05,
694
+ "loss": 0.1552,
695
  "step": 830
696
  },
697
  {
698
+ "epoch": 0.10277743790529793,
699
+ "grad_norm": 0.34810611605644226,
700
+ "learning_rate": 1.960004549534567e-05,
701
+ "loss": 0.1663,
702
  "step": 840
703
  },
704
  {
705
+ "epoch": 0.10400097883274195,
706
+ "grad_norm": 0.15511688590049744,
707
+ "learning_rate": 1.957682749948307e-05,
708
+ "loss": 0.1571,
709
  "step": 850
710
  },
711
  {
712
+ "epoch": 0.10522451976018597,
713
+ "grad_norm": 0.2082190364599228,
714
+ "learning_rate": 1.9552969006303666e-05,
715
+ "loss": 0.1497,
716
  "step": 860
717
  },
718
  {
719
+ "epoch": 0.10644806068763,
720
+ "grad_norm": 0.14936988055706024,
721
+ "learning_rate": 1.9528471611461235e-05,
722
+ "loss": 0.1435,
723
  "step": 870
724
  },
725
  {
726
+ "epoch": 0.10767160161507403,
727
+ "grad_norm": 0.252530574798584,
728
+ "learning_rate": 1.9503336953339223e-05,
729
+ "loss": 0.1536,
730
  "step": 880
731
  },
732
  {
733
+ "epoch": 0.10889514254251804,
734
+ "grad_norm": 0.07253506034612656,
735
+ "learning_rate": 1.947756671294118e-05,
736
+ "loss": 0.1605,
737
  "step": 890
738
  },
739
  {
740
+ "epoch": 0.11011868346996206,
741
+ "grad_norm": 0.09060605615377426,
742
+ "learning_rate": 1.9451162613778353e-05,
743
+ "loss": 0.1581,
744
+ "step": 900
745
+ },
746
+ {
747
+ "epoch": 0.11011868346996206,
748
+ "eval_accuracy": 0.95459,
749
+ "eval_f1_weighted": 0.9546135918699761,
750
+ "eval_loss": 0.03526490181684494,
751
+ "eval_macro_f1": 0.9545725664001194,
752
+ "eval_precision": 0.9559789658562307,
753
+ "eval_recall": 0.95459,
754
+ "eval_runtime": 759.7202,
755
+ "eval_samples_per_second": 131.627,
756
+ "eval_steps_per_second": 1.029,
757
  "step": 900
758
  },
759
  {
760
+ "epoch": 0.1113422243974061,
761
+ "grad_norm": 0.21080073714256287,
762
+ "learning_rate": 1.942412642175439e-05,
763
+ "loss": 0.164,
764
  "step": 910
765
  },
766
  {
767
+ "epoch": 0.11256576532485012,
768
+ "grad_norm": 0.22832269966602325,
769
+ "learning_rate": 1.939645994504726e-05,
770
+ "loss": 0.1595,
771
  "step": 920
772
  },
773
  {
774
+ "epoch": 0.11378930625229414,
775
+ "grad_norm": 0.19044892489910126,
776
+ "learning_rate": 1.93681650339883e-05,
777
+ "loss": 0.1648,
778
  "step": 930
779
  },
780
  {
781
+ "epoch": 0.11501284717973816,
782
+ "grad_norm": 0.2413518726825714,
783
+ "learning_rate": 1.9339243580938493e-05,
784
+ "loss": 0.155,
785
  "step": 940
786
  },
787
  {
788
+ "epoch": 0.11623638810718219,
789
+ "grad_norm": 0.13218896090984344,
790
+ "learning_rate": 1.930969752016187e-05,
791
+ "loss": 0.1499,
792
  "step": 950
793
  },
794
  {
795
+ "epoch": 0.11745992903462621,
796
+ "grad_norm": 0.23770441114902496,
797
+ "learning_rate": 1.927952882769619e-05,
798
+ "loss": 0.1555,
799
  "step": 960
800
  },
801
  {
802
+ "epoch": 0.11868346996207023,
803
+ "grad_norm": 0.2193710207939148,
804
+ "learning_rate": 1.924873952122074e-05,
805
+ "loss": 0.1505,
806
  "step": 970
807
  },
808
  {
809
+ "epoch": 0.11990701088951425,
810
+ "grad_norm": 0.1577174812555313,
811
+ "learning_rate": 1.9217331659921432e-05,
812
+ "loss": 0.1551,
813
  "step": 980
814
  },
815
  {
816
+ "epoch": 0.12113055181695828,
817
+ "grad_norm": 0.1814967393875122,
818
+ "learning_rate": 1.9185307344353052e-05,
819
+ "loss": 0.1607,
820
  "step": 990
821
  },
822
  {
823
+ "epoch": 0.1223540927444023,
824
+ "grad_norm": 0.27239707112312317,
825
+ "learning_rate": 1.91526687162988e-05,
826
+ "loss": 0.1506,
827
  "step": 1000
828
  },
829
  {
830
+ "epoch": 0.1223540927444023,
831
+ "eval_accuracy": 0.96454,
832
+ "eval_f1_weighted": 0.9645510150201642,
833
+ "eval_loss": 0.028770776465535164,
834
+ "eval_macro_f1": 0.9644889377060355,
835
+ "eval_precision": 0.9646912114769961,
836
+ "eval_recall": 0.96454,
837
+ "eval_runtime": 759.5962,
838
+ "eval_samples_per_second": 131.649,
839
+ "eval_steps_per_second": 1.029,
840
  "step": 1000
841
  }
842
  ],
843
  "logging_steps": 10,
844
+ "max_steps": 8173,
845
  "num_input_tokens_seen": 0,
846
  "num_train_epochs": 1,
847
+ "save_steps": 100,
848
  "stateful_callbacks": {
849
  "EarlyStoppingCallback": {
850
  "args": {
 
866
  "attributes": {}
867
  }
868
  },
869
+ "total_flos": 1.6974575173632e+16,
870
+ "train_batch_size": 64,
871
  "trial_name": null,
872
  "trial_params": null
873
  }
checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a51c9ce1080123075e6ab993dc495e2fe9920836854bf1888707e1cdafdc082
3
- size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84799314bcc123b16dc7e721b7c0a39a7148ba4c572d589c671664f2e203e207
3
+ size 5841
checkpoint-1100/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 1026,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "problem_type": "single_label_classification",
25
+ "transformers_version": "4.56.0",
26
+ "type_vocab_size": 10,
27
+ "use_cache": true,
28
+ "vocab_size": 51416
29
+ }
checkpoint-1100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b10c733460151c1d6f8993106b670307a2bb4c4b61d05e3eae7347702daac47
3
+ size 506505672
checkpoint-1100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53bf52cb642b51369e0a95075a5b756e85921ef6f4dc7f444e6cfe7fe2a5900c
3
+ size 1007622411
checkpoint-1100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c7c55a742bcfca5f903384e20f8e91ee2f8d2f9879952f810307a3ce3992b6
3
+ size 14645
checkpoint-1100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29c159530c0b045d9326d40e787007ff4922dc4adeb35441be0870744bf816a6
3
+ size 1383
checkpoint-1100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c167e18770e153a7e8f12beebdae3ca1a3d373a59d87ddaedaa9c151bac765
3
+ size 1977
checkpoint-1100/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-1100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1100/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-1100/trainer_state.json ADDED
@@ -0,0 +1,956 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 0.9644889377060355,
4
+ "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-1000",
5
+ "epoch": 0.13458950201884254,
6
+ "eval_steps": 100,
7
+ "global_step": 1100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.001223540927444023,
14
+ "grad_norm": 0.1898110806941986,
15
+ "learning_rate": 3.6734693877551025e-07,
16
+ "loss": 0.4422,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.002447081854888046,
21
+ "grad_norm": 0.3350900411605835,
22
+ "learning_rate": 7.346938775510205e-07,
23
+ "loss": 0.4323,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.003670622782332069,
28
+ "grad_norm": 0.3723449110984802,
29
+ "learning_rate": 1.142857142857143e-06,
30
+ "loss": 0.4362,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.004894163709776092,
35
+ "grad_norm": 0.3299769461154938,
36
+ "learning_rate": 1.5510204081632654e-06,
37
+ "loss": 0.4191,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.006117704637220115,
42
+ "grad_norm": 0.26681044697761536,
43
+ "learning_rate": 1.9591836734693877e-06,
44
+ "loss": 0.4289,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.007341245564664138,
49
+ "grad_norm": 0.30233338475227356,
50
+ "learning_rate": 2.3673469387755103e-06,
51
+ "loss": 0.4083,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.008564786492108161,
56
+ "grad_norm": 0.31031334400177,
57
+ "learning_rate": 2.775510204081633e-06,
58
+ "loss": 0.404,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.009788327419552184,
63
+ "grad_norm": 0.2552475035190582,
64
+ "learning_rate": 3.183673469387755e-06,
65
+ "loss": 0.3889,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.011011868346996207,
70
+ "grad_norm": 0.3131052553653717,
71
+ "learning_rate": 3.5918367346938777e-06,
72
+ "loss": 0.3813,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.01223540927444023,
77
+ "grad_norm": 0.3377229571342468,
78
+ "learning_rate": 4.000000000000001e-06,
79
+ "loss": 0.3727,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.01223540927444023,
84
+ "eval_accuracy": 0.6961,
85
+ "eval_f1_weighted": 0.6955947095331424,
86
+ "eval_loss": 0.15026023983955383,
87
+ "eval_macro_f1": 0.6959280508399847,
88
+ "eval_precision": 0.7019396279846728,
89
+ "eval_recall": 0.6961,
90
+ "eval_runtime": 789.7648,
91
+ "eval_samples_per_second": 126.62,
92
+ "eval_steps_per_second": 0.99,
93
+ "step": 100
94
+ },
95
+ {
96
+ "epoch": 0.013458950201884253,
97
+ "grad_norm": 0.3366774618625641,
98
+ "learning_rate": 4.408163265306123e-06,
99
+ "loss": 0.3671,
100
+ "step": 110
101
+ },
102
+ {
103
+ "epoch": 0.014682491129328276,
104
+ "grad_norm": 0.33491575717926025,
105
+ "learning_rate": 4.816326530612245e-06,
106
+ "loss": 0.3498,
107
+ "step": 120
108
+ },
109
+ {
110
+ "epoch": 0.0159060320567723,
111
+ "grad_norm": 0.4119006097316742,
112
+ "learning_rate": 5.2244897959183684e-06,
113
+ "loss": 0.3409,
114
+ "step": 130
115
+ },
116
+ {
117
+ "epoch": 0.017129572984216322,
118
+ "grad_norm": 0.2964725196361542,
119
+ "learning_rate": 5.63265306122449e-06,
120
+ "loss": 0.3433,
121
+ "step": 140
122
+ },
123
+ {
124
+ "epoch": 0.018353113911660345,
125
+ "grad_norm": 0.3075334429740906,
126
+ "learning_rate": 6.040816326530613e-06,
127
+ "loss": 0.3298,
128
+ "step": 150
129
+ },
130
+ {
131
+ "epoch": 0.019576654839104368,
132
+ "grad_norm": 0.33718687295913696,
133
+ "learning_rate": 6.4489795918367345e-06,
134
+ "loss": 0.3297,
135
+ "step": 160
136
+ },
137
+ {
138
+ "epoch": 0.02080019576654839,
139
+ "grad_norm": 0.2809618413448334,
140
+ "learning_rate": 6.857142857142858e-06,
141
+ "loss": 0.3275,
142
+ "step": 170
143
+ },
144
+ {
145
+ "epoch": 0.022023736693992414,
146
+ "grad_norm": 0.37805014848709106,
147
+ "learning_rate": 7.2653061224489805e-06,
148
+ "loss": 0.3201,
149
+ "step": 180
150
+ },
151
+ {
152
+ "epoch": 0.023247277621436437,
153
+ "grad_norm": 0.2940429151058197,
154
+ "learning_rate": 7.673469387755102e-06,
155
+ "loss": 0.3042,
156
+ "step": 190
157
+ },
158
+ {
159
+ "epoch": 0.02447081854888046,
160
+ "grad_norm": 0.3286060690879822,
161
+ "learning_rate": 8.081632653061225e-06,
162
+ "loss": 0.3071,
163
+ "step": 200
164
+ },
165
+ {
166
+ "epoch": 0.02447081854888046,
167
+ "eval_accuracy": 0.77807,
168
+ "eval_f1_weighted": 0.7781129395311969,
169
+ "eval_loss": 0.12153773754835129,
170
+ "eval_macro_f1": 0.7780651598452646,
171
+ "eval_precision": 0.7808306361972198,
172
+ "eval_recall": 0.77807,
173
+ "eval_runtime": 792.7157,
174
+ "eval_samples_per_second": 126.149,
175
+ "eval_steps_per_second": 0.986,
176
+ "step": 200
177
+ },
178
+ {
179
+ "epoch": 0.025694359476324483,
180
+ "grad_norm": 0.33857154846191406,
181
+ "learning_rate": 8.489795918367347e-06,
182
+ "loss": 0.2964,
183
+ "step": 210
184
+ },
185
+ {
186
+ "epoch": 0.026917900403768506,
187
+ "grad_norm": 0.2752092182636261,
188
+ "learning_rate": 8.89795918367347e-06,
189
+ "loss": 0.3,
190
+ "step": 220
191
+ },
192
+ {
193
+ "epoch": 0.02814144133121253,
194
+ "grad_norm": 0.4952544569969177,
195
+ "learning_rate": 9.306122448979593e-06,
196
+ "loss": 0.294,
197
+ "step": 230
198
+ },
199
+ {
200
+ "epoch": 0.029364982258656552,
201
+ "grad_norm": 0.37926042079925537,
202
+ "learning_rate": 9.714285714285715e-06,
203
+ "loss": 0.2964,
204
+ "step": 240
205
+ },
206
+ {
207
+ "epoch": 0.030588523186100575,
208
+ "grad_norm": 0.3222455680370331,
209
+ "learning_rate": 1.0122448979591836e-05,
210
+ "loss": 0.283,
211
+ "step": 250
212
+ },
213
+ {
214
+ "epoch": 0.0318120641135446,
215
+ "grad_norm": 0.2930658459663391,
216
+ "learning_rate": 1.053061224489796e-05,
217
+ "loss": 0.2793,
218
+ "step": 260
219
+ },
220
+ {
221
+ "epoch": 0.03303560504098862,
222
+ "grad_norm": 0.4313414692878723,
223
+ "learning_rate": 1.0938775510204083e-05,
224
+ "loss": 0.2728,
225
+ "step": 270
226
+ },
227
+ {
228
+ "epoch": 0.034259145968432644,
229
+ "grad_norm": 0.37351569533348083,
230
+ "learning_rate": 1.1346938775510206e-05,
231
+ "loss": 0.2752,
232
+ "step": 280
233
+ },
234
+ {
235
+ "epoch": 0.035482686895876664,
236
+ "grad_norm": 0.22772285342216492,
237
+ "learning_rate": 1.1755102040816328e-05,
238
+ "loss": 0.274,
239
+ "step": 290
240
+ },
241
+ {
242
+ "epoch": 0.03670622782332069,
243
+ "grad_norm": 0.15888753533363342,
244
+ "learning_rate": 1.2163265306122449e-05,
245
+ "loss": 0.264,
246
+ "step": 300
247
+ },
248
+ {
249
+ "epoch": 0.03670622782332069,
250
+ "eval_accuracy": 0.82326,
251
+ "eval_f1_weighted": 0.8227034206790359,
252
+ "eval_loss": 0.10234300792217255,
253
+ "eval_macro_f1": 0.8230100448030374,
254
+ "eval_precision": 0.8338333810964687,
255
+ "eval_recall": 0.82326,
256
+ "eval_runtime": 789.0168,
257
+ "eval_samples_per_second": 126.74,
258
+ "eval_steps_per_second": 0.991,
259
+ "step": 300
260
+ },
261
+ {
262
+ "epoch": 0.03792976875076471,
263
+ "grad_norm": 0.23560188710689545,
264
+ "learning_rate": 1.2571428571428572e-05,
265
+ "loss": 0.2753,
266
+ "step": 310
267
+ },
268
+ {
269
+ "epoch": 0.039153309678208736,
270
+ "grad_norm": 0.18699614703655243,
271
+ "learning_rate": 1.2979591836734696e-05,
272
+ "loss": 0.2565,
273
+ "step": 320
274
+ },
275
+ {
276
+ "epoch": 0.040376850605652756,
277
+ "grad_norm": 0.24035991728305817,
278
+ "learning_rate": 1.3387755102040818e-05,
279
+ "loss": 0.2716,
280
+ "step": 330
281
+ },
282
+ {
283
+ "epoch": 0.04160039153309678,
284
+ "grad_norm": 0.15309660136699677,
285
+ "learning_rate": 1.3795918367346941e-05,
286
+ "loss": 0.2515,
287
+ "step": 340
288
+ },
289
+ {
290
+ "epoch": 0.0428239324605408,
291
+ "grad_norm": 0.3382055461406708,
292
+ "learning_rate": 1.4204081632653062e-05,
293
+ "loss": 0.2597,
294
+ "step": 350
295
+ },
296
+ {
297
+ "epoch": 0.04404747338798483,
298
+ "grad_norm": 0.24439455568790436,
299
+ "learning_rate": 1.4612244897959185e-05,
300
+ "loss": 0.247,
301
+ "step": 360
302
+ },
303
+ {
304
+ "epoch": 0.04527101431542885,
305
+ "grad_norm": 0.26233720779418945,
306
+ "learning_rate": 1.5020408163265307e-05,
307
+ "loss": 0.2431,
308
+ "step": 370
309
+ },
310
+ {
311
+ "epoch": 0.046494555242872875,
312
+ "grad_norm": 0.20477451384067535,
313
+ "learning_rate": 1.5387755102040818e-05,
314
+ "loss": 0.2538,
315
+ "step": 380
316
+ },
317
+ {
318
+ "epoch": 0.047718096170316894,
319
+ "grad_norm": 0.2765439748764038,
320
+ "learning_rate": 1.5795918367346942e-05,
321
+ "loss": 0.2404,
322
+ "step": 390
323
+ },
324
+ {
325
+ "epoch": 0.04894163709776092,
326
+ "grad_norm": 0.13196279108524323,
327
+ "learning_rate": 1.6204081632653063e-05,
328
+ "loss": 0.2393,
329
+ "step": 400
330
+ },
331
+ {
332
+ "epoch": 0.04894163709776092,
333
+ "eval_accuracy": 0.84563,
334
+ "eval_f1_weighted": 0.8448128964509274,
335
+ "eval_loss": 0.09028046578168869,
336
+ "eval_macro_f1": 0.8451923512067675,
337
+ "eval_precision": 0.861024732271907,
338
+ "eval_recall": 0.84563,
339
+ "eval_runtime": 787.6067,
340
+ "eval_samples_per_second": 126.967,
341
+ "eval_steps_per_second": 0.993,
342
+ "step": 400
343
+ },
344
+ {
345
+ "epoch": 0.05016517802520494,
346
+ "grad_norm": 0.0924634337425232,
347
+ "learning_rate": 1.6612244897959184e-05,
348
+ "loss": 0.2331,
349
+ "step": 410
350
+ },
351
+ {
352
+ "epoch": 0.05138871895264897,
353
+ "grad_norm": 0.277784138917923,
354
+ "learning_rate": 1.7020408163265308e-05,
355
+ "loss": 0.2301,
356
+ "step": 420
357
+ },
358
+ {
359
+ "epoch": 0.052612259880092986,
360
+ "grad_norm": 0.32299959659576416,
361
+ "learning_rate": 1.742857142857143e-05,
362
+ "loss": 0.2218,
363
+ "step": 430
364
+ },
365
+ {
366
+ "epoch": 0.05383580080753701,
367
+ "grad_norm": 0.18170586228370667,
368
+ "learning_rate": 1.7836734693877553e-05,
369
+ "loss": 0.2318,
370
+ "step": 440
371
+ },
372
+ {
373
+ "epoch": 0.05505934173498103,
374
+ "grad_norm": 0.1520216166973114,
375
+ "learning_rate": 1.8244897959183674e-05,
376
+ "loss": 0.2136,
377
+ "step": 450
378
+ },
379
+ {
380
+ "epoch": 0.05628288266242506,
381
+ "grad_norm": 0.23452645540237427,
382
+ "learning_rate": 1.8653061224489795e-05,
383
+ "loss": 0.2219,
384
+ "step": 460
385
+ },
386
+ {
387
+ "epoch": 0.05750642358986908,
388
+ "grad_norm": 0.10036301612854004,
389
+ "learning_rate": 1.906122448979592e-05,
390
+ "loss": 0.2213,
391
+ "step": 470
392
+ },
393
+ {
394
+ "epoch": 0.058729964517313105,
395
+ "grad_norm": 0.24100220203399658,
396
+ "learning_rate": 1.9469387755102044e-05,
397
+ "loss": 0.2079,
398
+ "step": 480
399
+ },
400
+ {
401
+ "epoch": 0.059953505444757124,
402
+ "grad_norm": 0.28893032670021057,
403
+ "learning_rate": 1.9877551020408165e-05,
404
+ "loss": 0.1978,
405
+ "step": 490
406
+ },
407
+ {
408
+ "epoch": 0.06117704637220115,
409
+ "grad_norm": 0.22918537259101868,
410
+ "learning_rate": 1.9999836143766126e-05,
411
+ "loss": 0.202,
412
+ "step": 500
413
+ },
414
+ {
415
+ "epoch": 0.06117704637220115,
416
+ "eval_accuracy": 0.91628,
417
+ "eval_f1_weighted": 0.9163231793856368,
418
+ "eval_loss": 0.055908624082803726,
419
+ "eval_macro_f1": 0.9162187423616152,
420
+ "eval_precision": 0.9170320825159874,
421
+ "eval_recall": 0.91628,
422
+ "eval_runtime": 760.1138,
423
+ "eval_samples_per_second": 131.559,
424
+ "eval_steps_per_second": 1.029,
425
+ "step": 500
426
+ },
427
+ {
428
+ "epoch": 0.06240058729964517,
429
+ "grad_norm": 0.2930404841899872,
430
+ "learning_rate": 1.999903359554741e-05,
431
+ "loss": 0.1979,
432
+ "step": 510
433
+ },
434
+ {
435
+ "epoch": 0.0636241282270892,
436
+ "grad_norm": 0.0889664739370346,
437
+ "learning_rate": 1.9997562312908153e-05,
438
+ "loss": 0.1953,
439
+ "step": 520
440
+ },
441
+ {
442
+ "epoch": 0.06484766915453322,
443
+ "grad_norm": 0.1687588095664978,
444
+ "learning_rate": 1.9995422394247598e-05,
445
+ "loss": 0.1935,
446
+ "step": 530
447
+ },
448
+ {
449
+ "epoch": 0.06607121008197724,
450
+ "grad_norm": 0.2399725466966629,
451
+ "learning_rate": 1.9992613982683296e-05,
452
+ "loss": 0.1818,
453
+ "step": 540
454
+ },
455
+ {
456
+ "epoch": 0.06729475100942127,
457
+ "grad_norm": 0.2016785889863968,
458
+ "learning_rate": 1.9989137266041552e-05,
459
+ "loss": 0.1893,
460
+ "step": 550
461
+ },
462
+ {
463
+ "epoch": 0.06851829193686529,
464
+ "grad_norm": 0.17420713603496552,
465
+ "learning_rate": 1.9984992476844845e-05,
466
+ "loss": 0.1895,
467
+ "step": 560
468
+ },
469
+ {
470
+ "epoch": 0.06974183286430931,
471
+ "grad_norm": 0.2180609554052353,
472
+ "learning_rate": 1.998017989229629e-05,
473
+ "loss": 0.1836,
474
+ "step": 570
475
+ },
476
+ {
477
+ "epoch": 0.07096537379175333,
478
+ "grad_norm": 0.15563039481639862,
479
+ "learning_rate": 1.9974699834261074e-05,
480
+ "loss": 0.182,
481
+ "step": 580
482
+ },
483
+ {
484
+ "epoch": 0.07218891471919736,
485
+ "grad_norm": 0.25410088896751404,
486
+ "learning_rate": 1.996855266924497e-05,
487
+ "loss": 0.1862,
488
+ "step": 590
489
+ },
490
+ {
491
+ "epoch": 0.07341245564664138,
492
+ "grad_norm": 0.24206259846687317,
493
+ "learning_rate": 1.996173880836979e-05,
494
+ "loss": 0.1818,
495
+ "step": 600
496
+ },
497
+ {
498
+ "epoch": 0.07341245564664138,
499
+ "eval_accuracy": 0.91633,
500
+ "eval_f1_weighted": 0.9162437523349878,
501
+ "eval_loss": 0.05625538155436516,
502
+ "eval_macro_f1": 0.9163072974421806,
503
+ "eval_precision": 0.9233764457540103,
504
+ "eval_recall": 0.91633,
505
+ "eval_runtime": 759.6815,
506
+ "eval_samples_per_second": 131.634,
507
+ "eval_steps_per_second": 1.029,
508
+ "step": 600
509
+ },
510
+ {
511
+ "epoch": 0.0746359965740854,
512
+ "grad_norm": 0.27251410484313965,
513
+ "learning_rate": 1.9954258707345903e-05,
514
+ "loss": 0.1845,
515
+ "step": 610
516
+ },
517
+ {
518
+ "epoch": 0.07585953750152942,
519
+ "grad_norm": 0.1545839011669159,
520
+ "learning_rate": 1.9946112866441757e-05,
521
+ "loss": 0.1861,
522
+ "step": 620
523
+ },
524
+ {
525
+ "epoch": 0.07708307842897345,
526
+ "grad_norm": 0.2535873055458069,
527
+ "learning_rate": 1.9937301830450423e-05,
528
+ "loss": 0.1772,
529
+ "step": 630
530
+ },
531
+ {
532
+ "epoch": 0.07830661935641747,
533
+ "grad_norm": 0.2617948651313782,
534
+ "learning_rate": 1.992782618865315e-05,
535
+ "loss": 0.1711,
536
+ "step": 640
537
+ },
538
+ {
539
+ "epoch": 0.07953016028386149,
540
+ "grad_norm": 0.38676971197128296,
541
+ "learning_rate": 1.9917686574779972e-05,
542
+ "loss": 0.1748,
543
+ "step": 650
544
+ },
545
+ {
546
+ "epoch": 0.08075370121130551,
547
+ "grad_norm": 0.1511957049369812,
548
+ "learning_rate": 1.9906883666967296e-05,
549
+ "loss": 0.1825,
550
+ "step": 660
551
+ },
552
+ {
553
+ "epoch": 0.08197724213874955,
554
+ "grad_norm": 0.2525976002216339,
555
+ "learning_rate": 1.989541818771258e-05,
556
+ "loss": 0.1651,
557
+ "step": 670
558
+ },
559
+ {
560
+ "epoch": 0.08320078306619356,
561
+ "grad_norm": 0.25827622413635254,
562
+ "learning_rate": 1.9883290903825994e-05,
563
+ "loss": 0.1763,
564
+ "step": 680
565
+ },
566
+ {
567
+ "epoch": 0.08442432399363758,
568
+ "grad_norm": 0.24877820909023285,
569
+ "learning_rate": 1.9870502626379127e-05,
570
+ "loss": 0.1652,
571
+ "step": 690
572
+ },
573
+ {
574
+ "epoch": 0.0856478649210816,
575
+ "grad_norm": 0.278772234916687,
576
+ "learning_rate": 1.9857054210650776e-05,
577
+ "loss": 0.1651,
578
+ "step": 700
579
+ },
580
+ {
581
+ "epoch": 0.0856478649210816,
582
+ "eval_accuracy": 0.94905,
583
+ "eval_f1_weighted": 0.9490731118481598,
584
+ "eval_loss": 0.03884471580386162,
585
+ "eval_macro_f1": 0.9489981325237288,
586
+ "eval_precision": 0.9494795831024372,
587
+ "eval_recall": 0.94905,
588
+ "eval_runtime": 759.9337,
589
+ "eval_samples_per_second": 131.59,
590
+ "eval_steps_per_second": 1.029,
591
+ "step": 700
592
+ },
593
+ {
594
+ "epoch": 0.08687140584852564,
595
+ "grad_norm": 0.1895805150270462,
596
+ "learning_rate": 1.9842946556069705e-05,
597
+ "loss": 0.1628,
598
+ "step": 710
599
+ },
600
+ {
601
+ "epoch": 0.08809494677596966,
602
+ "grad_norm": 0.1171497106552124,
603
+ "learning_rate": 1.982818060615452e-05,
604
+ "loss": 0.1715,
605
+ "step": 720
606
+ },
607
+ {
608
+ "epoch": 0.08931848770341368,
609
+ "grad_norm": 0.22032728791236877,
610
+ "learning_rate": 1.9812757348450547e-05,
611
+ "loss": 0.1712,
612
+ "step": 730
613
+ },
614
+ {
615
+ "epoch": 0.0905420286308577,
616
+ "grad_norm": 0.20700488984584808,
617
+ "learning_rate": 1.9796677814463812e-05,
618
+ "loss": 0.1638,
619
+ "step": 740
620
+ },
621
+ {
622
+ "epoch": 0.09176556955830173,
623
+ "grad_norm": 0.24688613414764404,
624
+ "learning_rate": 1.977994307959202e-05,
625
+ "loss": 0.1647,
626
+ "step": 750
627
+ },
628
+ {
629
+ "epoch": 0.09298911048574575,
630
+ "grad_norm": 0.1886432021856308,
631
+ "learning_rate": 1.9762554263052655e-05,
632
+ "loss": 0.1734,
633
+ "step": 760
634
+ },
635
+ {
636
+ "epoch": 0.09421265141318977,
637
+ "grad_norm": 0.08407370001077652,
638
+ "learning_rate": 1.9744512527808127e-05,
639
+ "loss": 0.1755,
640
+ "step": 770
641
+ },
642
+ {
643
+ "epoch": 0.09543619234063379,
644
+ "grad_norm": 0.14160771667957306,
645
+ "learning_rate": 1.9725819080487976e-05,
646
+ "loss": 0.1749,
647
+ "step": 780
648
+ },
649
+ {
650
+ "epoch": 0.09665973326807782,
651
+ "grad_norm": 0.17038081586360931,
652
+ "learning_rate": 1.970647517130819e-05,
653
+ "loss": 0.1795,
654
+ "step": 790
655
+ },
656
+ {
657
+ "epoch": 0.09788327419552184,
658
+ "grad_norm": 0.24339532852172852,
659
+ "learning_rate": 1.968648209398759e-05,
660
+ "loss": 0.161,
661
+ "step": 800
662
+ },
663
+ {
664
+ "epoch": 0.09788327419552184,
665
+ "eval_accuracy": 0.95721,
666
+ "eval_f1_weighted": 0.9572295598206603,
667
+ "eval_loss": 0.03337462991476059,
668
+ "eval_macro_f1": 0.9571669846830866,
669
+ "eval_precision": 0.9576467364395861,
670
+ "eval_recall": 0.95721,
671
+ "eval_runtime": 759.9975,
672
+ "eval_samples_per_second": 131.579,
673
+ "eval_steps_per_second": 1.029,
674
+ "step": 800
675
+ },
676
+ {
677
+ "epoch": 0.09910681512296586,
678
+ "grad_norm": 0.16346058249473572,
679
+ "learning_rate": 1.9665841185661283e-05,
680
+ "loss": 0.1596,
681
+ "step": 810
682
+ },
683
+ {
684
+ "epoch": 0.10033035605040988,
685
+ "grad_norm": 0.25031423568725586,
686
+ "learning_rate": 1.964455382679128e-05,
687
+ "loss": 0.1662,
688
+ "step": 820
689
+ },
690
+ {
691
+ "epoch": 0.10155389697785391,
692
+ "grad_norm": 0.36678382754325867,
693
+ "learning_rate": 1.9622621441074113e-05,
694
+ "loss": 0.1552,
695
+ "step": 830
696
+ },
697
+ {
698
+ "epoch": 0.10277743790529793,
699
+ "grad_norm": 0.34810611605644226,
700
+ "learning_rate": 1.960004549534567e-05,
701
+ "loss": 0.1663,
702
+ "step": 840
703
+ },
704
+ {
705
+ "epoch": 0.10400097883274195,
706
+ "grad_norm": 0.15511688590049744,
707
+ "learning_rate": 1.957682749948307e-05,
708
+ "loss": 0.1571,
709
+ "step": 850
710
+ },
711
+ {
712
+ "epoch": 0.10522451976018597,
713
+ "grad_norm": 0.2082190364599228,
714
+ "learning_rate": 1.9552969006303666e-05,
715
+ "loss": 0.1497,
716
+ "step": 860
717
+ },
718
+ {
719
+ "epoch": 0.10644806068763,
720
+ "grad_norm": 0.14936988055706024,
721
+ "learning_rate": 1.9528471611461235e-05,
722
+ "loss": 0.1435,
723
+ "step": 870
724
+ },
725
+ {
726
+ "epoch": 0.10767160161507403,
727
+ "grad_norm": 0.252530574798584,
728
+ "learning_rate": 1.9503336953339223e-05,
729
+ "loss": 0.1536,
730
+ "step": 880
731
+ },
732
+ {
733
+ "epoch": 0.10889514254251804,
734
+ "grad_norm": 0.07253506034612656,
735
+ "learning_rate": 1.947756671294118e-05,
736
+ "loss": 0.1605,
737
+ "step": 890
738
+ },
739
+ {
740
+ "epoch": 0.11011868346996206,
741
+ "grad_norm": 0.09060605615377426,
742
+ "learning_rate": 1.9451162613778353e-05,
743
+ "loss": 0.1581,
744
+ "step": 900
745
+ },
746
+ {
747
+ "epoch": 0.11011868346996206,
748
+ "eval_accuracy": 0.95459,
749
+ "eval_f1_weighted": 0.9546135918699761,
750
+ "eval_loss": 0.03526490181684494,
751
+ "eval_macro_f1": 0.9545725664001194,
752
+ "eval_precision": 0.9559789658562307,
753
+ "eval_recall": 0.95459,
754
+ "eval_runtime": 759.7202,
755
+ "eval_samples_per_second": 131.627,
756
+ "eval_steps_per_second": 1.029,
757
+ "step": 900
758
+ },
759
+ {
760
+ "epoch": 0.1113422243974061,
761
+ "grad_norm": 0.21080073714256287,
762
+ "learning_rate": 1.942412642175439e-05,
763
+ "loss": 0.164,
764
+ "step": 910
765
+ },
766
+ {
767
+ "epoch": 0.11256576532485012,
768
+ "grad_norm": 0.22832269966602325,
769
+ "learning_rate": 1.939645994504726e-05,
770
+ "loss": 0.1595,
771
+ "step": 920
772
+ },
773
+ {
774
+ "epoch": 0.11378930625229414,
775
+ "grad_norm": 0.19044892489910126,
776
+ "learning_rate": 1.93681650339883e-05,
777
+ "loss": 0.1648,
778
+ "step": 930
779
+ },
780
+ {
781
+ "epoch": 0.11501284717973816,
782
+ "grad_norm": 0.2413518726825714,
783
+ "learning_rate": 1.9339243580938493e-05,
784
+ "loss": 0.155,
785
+ "step": 940
786
+ },
787
+ {
788
+ "epoch": 0.11623638810718219,
789
+ "grad_norm": 0.13218896090984344,
790
+ "learning_rate": 1.930969752016187e-05,
791
+ "loss": 0.1499,
792
+ "step": 950
793
+ },
794
+ {
795
+ "epoch": 0.11745992903462621,
796
+ "grad_norm": 0.23770441114902496,
797
+ "learning_rate": 1.927952882769619e-05,
798
+ "loss": 0.1555,
799
+ "step": 960
800
+ },
801
+ {
802
+ "epoch": 0.11868346996207023,
803
+ "grad_norm": 0.2193710207939148,
804
+ "learning_rate": 1.924873952122074e-05,
805
+ "loss": 0.1505,
806
+ "step": 970
807
+ },
808
+ {
809
+ "epoch": 0.11990701088951425,
810
+ "grad_norm": 0.1577174812555313,
811
+ "learning_rate": 1.9217331659921432e-05,
812
+ "loss": 0.1551,
813
+ "step": 980
814
+ },
815
+ {
816
+ "epoch": 0.12113055181695828,
817
+ "grad_norm": 0.1814967393875122,
818
+ "learning_rate": 1.9185307344353052e-05,
819
+ "loss": 0.1607,
820
+ "step": 990
821
+ },
822
+ {
823
+ "epoch": 0.1223540927444023,
824
+ "grad_norm": 0.27239707112312317,
825
+ "learning_rate": 1.91526687162988e-05,
826
+ "loss": 0.1506,
827
+ "step": 1000
828
+ },
829
+ {
830
+ "epoch": 0.1223540927444023,
831
+ "eval_accuracy": 0.96454,
832
+ "eval_f1_weighted": 0.9645510150201642,
833
+ "eval_loss": 0.028770776465535164,
834
+ "eval_macro_f1": 0.9644889377060355,
835
+ "eval_precision": 0.9646912114769961,
836
+ "eval_recall": 0.96454,
837
+ "eval_runtime": 759.5962,
838
+ "eval_samples_per_second": 131.649,
839
+ "eval_steps_per_second": 1.029,
840
+ "step": 1000
841
+ },
842
+ {
843
+ "epoch": 0.12357763367184632,
844
+ "grad_norm": 0.20511822402477264,
845
+ "learning_rate": 1.9119417958627022e-05,
846
+ "loss": 0.1503,
847
+ "step": 1010
848
+ },
849
+ {
850
+ "epoch": 0.12480117459929034,
851
+ "grad_norm": 0.2324151247739792,
852
+ "learning_rate": 1.9085557295145254e-05,
853
+ "loss": 0.1581,
854
+ "step": 1020
855
+ },
856
+ {
857
+ "epoch": 0.12602471552673436,
858
+ "grad_norm": 0.11019974201917648,
859
+ "learning_rate": 1.905108899045146e-05,
860
+ "loss": 0.1556,
861
+ "step": 1030
862
+ },
863
+ {
864
+ "epoch": 0.1272482564541784,
865
+ "grad_norm": 0.13370558619499207,
866
+ "learning_rate": 1.9016015349782594e-05,
867
+ "loss": 0.1469,
868
+ "step": 1040
869
+ },
870
+ {
871
+ "epoch": 0.12847179738162243,
872
+ "grad_norm": 0.11238931119441986,
873
+ "learning_rate": 1.8980338718860426e-05,
874
+ "loss": 0.155,
875
+ "step": 1050
876
+ },
877
+ {
878
+ "epoch": 0.12969533830906643,
879
+ "grad_norm": 0.2959650158882141,
880
+ "learning_rate": 1.894406148373466e-05,
881
+ "loss": 0.1478,
882
+ "step": 1060
883
+ },
884
+ {
885
+ "epoch": 0.13091887923651047,
886
+ "grad_norm": 0.14401015639305115,
887
+ "learning_rate": 1.890718607062334e-05,
888
+ "loss": 0.1558,
889
+ "step": 1070
890
+ },
891
+ {
892
+ "epoch": 0.13214242016395447,
893
+ "grad_norm": 0.2187667042016983,
894
+ "learning_rate": 1.8869714945750614e-05,
895
+ "loss": 0.1618,
896
+ "step": 1080
897
+ },
898
+ {
899
+ "epoch": 0.1333659610913985,
900
+ "grad_norm": 0.17045481503009796,
901
+ "learning_rate": 1.883165061518176e-05,
902
+ "loss": 0.1487,
903
+ "step": 1090
904
+ },
905
+ {
906
+ "epoch": 0.13458950201884254,
907
+ "grad_norm": 0.09508351981639862,
908
+ "learning_rate": 1.8792995624655605e-05,
909
+ "loss": 0.1461,
910
+ "step": 1100
911
+ },
912
+ {
913
+ "epoch": 0.13458950201884254,
914
+ "eval_accuracy": 0.95198,
915
+ "eval_f1_weighted": 0.9520023284947491,
916
+ "eval_loss": 0.04088817164301872,
917
+ "eval_macro_f1": 0.9519693367124435,
918
+ "eval_precision": 0.9538785423213092,
919
+ "eval_recall": 0.95198,
920
+ "eval_runtime": 759.8551,
921
+ "eval_samples_per_second": 131.604,
922
+ "eval_steps_per_second": 1.029,
923
+ "step": 1100
924
+ }
925
+ ],
926
+ "logging_steps": 10,
927
+ "max_steps": 8173,
928
+ "num_input_tokens_seen": 0,
929
+ "num_train_epochs": 1,
930
+ "save_steps": 100,
931
+ "stateful_callbacks": {
932
+ "EarlyStoppingCallback": {
933
+ "args": {
934
+ "early_stopping_patience": 3,
935
+ "early_stopping_threshold": 0.0
936
+ },
937
+ "attributes": {
938
+ "early_stopping_patience_counter": 1
939
+ }
940
+ },
941
+ "TrainerControl": {
942
+ "args": {
943
+ "should_epoch_stop": false,
944
+ "should_evaluate": false,
945
+ "should_log": false,
946
+ "should_save": true,
947
+ "should_training_stop": false
948
+ },
949
+ "attributes": {}
950
+ }
951
+ },
952
+ "total_flos": 1.86720326909952e+16,
953
+ "train_batch_size": 64,
954
+ "trial_name": null,
955
+ "trial_params": null
956
+ }
checkpoint-1100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84799314bcc123b16dc7e721b7c0a39a7148ba4c572d589c671664f2e203e207
3
+ size 5841
checkpoint-1100/vocab.json ADDED
The diff for this file is too large to render. See raw diff